From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
In order to avoid having to do put/set on a whole cgroup hierarchy
when we context switch, push the put into pick_next_task() so that
both operations are in the same function. Further changes then allow
us to possibly optimize away redundant work.
[ glommer@xxxxxxxxxx: incorporated mailing list feedback ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Glauber Costa <glommer@xxxxxxxxxx>
---
kernel/sched/core.c | 20 +++++++-------------
kernel/sched/fair.c | 6 +++++-
kernel/sched/idle_task.c | 6 +++++-
kernel/sched/rt.c | 27 ++++++++++++++++-----------
kernel/sched/sched.h | 8 +++++++-
kernel/sched/stop_task.c | 5 ++++-
6 files changed, 44 insertions(+), 28 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0fa0f87..3b1441f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2295,18 +2295,11 @@ static inline void schedule_debug(struct task_struct *prev)
schedstat_inc(this_rq(), sched_count);
}
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
- if (prev->on_rq || rq->skip_clock_update < 0)
- update_rq_clock(rq);
- prev->sched_class->put_prev_task(rq, prev);
-}
-
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
{
const struct sched_class *class;
struct task_struct *p;
@@ -2316,13 +2309,13 @@ pick_next_task(struct rq *rq)
* the fair class we can call that function directly:
*/
if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq);
+ p = fair_sched_class.pick_next_task(rq, prev);
if (likely(p))
return p;
}
for_each_class(class) {
- p = class->pick_next_task(rq);
+ p = class->pick_next_task(rq, prev);
if (p)
return p;
}
@@ -2417,8 +2410,9 @@ need_resched:
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
- put_prev_task(rq, prev);
- next = pick_next_task(rq);
+ if (prev->on_rq || rq->skip_clock_update < 0)
+ update_rq_clock(rq);
+ next = pick_next_task(rq, prev);
clear_tsk_need_resched(prev);
rq->skip_clock_update = 0;
@@ -4395,7 +4389,7 @@ static void migrate_tasks(unsigned int dead_cpu)
if (rq->nr_running == 1)
break;
- next = pick_next_task(rq);
+ next = pick_next_task(rq, NULL);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a7f5c39..414cf1c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3628,7 +3628,8 @@ preempt:
set_last_buddy(se);
}
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
{
struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
@@ -3637,6 +3638,9 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
if (!cfs_rq->nr_running)
return NULL;
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
+
do {
se = pick_next_entity(cfs_rq);
set_next_entity(cfs_rq, se);
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index d8da010..4f0a332 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -33,8 +33,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
resched_task(rq->idle);
}
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
{
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
+
schedstat_inc(rq, sched_goidle);
#ifdef CONFIG_SMP
/* Trigger the post schedule to do an idle_enter for CFS */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4a21045..6c41fa1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1330,15 +1330,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
struct sched_rt_entity *rt_se;
struct task_struct *p;
- struct rt_rq *rt_rq;
-
- rt_rq = &rq->rt;
-
- if (!rt_rq->rt_nr_running)
- return NULL;
-
- if (rt_rq_throttled(rt_rq))
- return NULL;
+ struct rt_rq *rt_rq = &rq->rt;
do {
rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1352,9 +1344,22 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
return p;
}
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
{
- struct task_struct *p = _pick_next_task_rt(rq);
+ struct task_struct *p;
+ struct rt_rq *rt_rq = &rq->rt;
+
+ if (!rt_rq->rt_nr_running)
+ return NULL;
+
+ if (rt_rq_throttled(rt_rq))
+ return NULL;
+
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
+
+ p = _pick_next_task_rt(rq);
/* The running task is never eligible for pushing */
if (p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0e5e795..a39eb9b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -987,7 +987,13 @@ struct sched_class {
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
- struct task_struct * (*pick_next_task) (struct rq *rq);
+ /*
+ * It is the responsibility of the pick_next_task() method that will
+ * return the next task to call put_prev_task() on the @prev task or
+ * something equivalent.
+ */
+ struct task_struct * (*pick_next_task) (struct rq *rq,
+ struct task_struct *prev);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 4142d7e..6adf6a9 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,12 +23,15 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
/* we're never preempted */
}
-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *stop = rq->stop;
if (stop && stop->on_rq) {
stop->se.exec_start = rq_clock_task(rq);
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
return stop;
}
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
